Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6623
    Prev
    Next
    INDEX
    Explanations

    names and terms related to legal, financial, and business contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities associated with governance and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chirop
    -0.66
    ilater
    -0.61
    cffff
    -0.61
    anwhile
    -0.61
    ruary
    -0.61
     crop
    -0.59
     coron
    -0.59
    ailability
    -0.58
    ÃĽ
    -0.58
    osponsors
    -0.58
    POSITIVE LOGITS
    tsky
    0.88
    kaya
    0.88
    adder
    0.75
    hare
    0.73
    oxide
    0.70
    bilt
    0.69
    lycer
    0.69
    anski
    0.67
    wark
    0.66
    achev
    0.65
    Activations Density 0.487%

    No Known Activations